Advertisement

Optimizing Hierarchical Temporal Memory for Multivariable Time Series

  • David Rozado
  • Francisco B. Rodriguez
  • Pablo Varona
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6353)

Abstract

Hierarchical Temporal Memory (HTM) is an emerging computational paradigm consisting of a hierarchically connected network of nodes. The hierarchy models a key design principle of neocortical organization. Nodes throughout the hierarchy encode information by means of clustering spatial instances within their receptive fields according to temporal proximity. Literature shows HTMs’ robust performance on traditional machine learning tasks such as image recognition. Problems involving multi-variable time series where instances unfold over time with no complete spatial representation at any point in time have proven trickier for HTMs. We have extended the traditional HTMs’ principles by means of a top node that stores and aligns sequences of input patterns representing the spatio-temporal structure of instances to be learned. This extended HTM network improves performance with respect to traditional HTMs in machine learning tasks whose input instances unfold over time.

Keywords

Optimal Topology Input Vector Child Node Parent Node Temporal Group 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    George, D., Hawkins, J.: Towards a mathematical theory of cortical micro-circuits. PLoS Comput. Biol. 5(10), e1000532 (2009)CrossRefGoogle Scholar
  2. 2.
    Hawkings, J.: Hierarchical temporal memory, concepts, theory, and terminology. Numenta, Tech. Rep. (2006)Google Scholar
  3. 3.
    George, D., Jarosy, B.: The HTM learning algorithms. Numenta, Tech. Rep. (2007)Google Scholar
  4. 4.
    Mountcastle, V.: The columnar organization of the neocortex. Brain 120(4), 701–722 (1997)CrossRefGoogle Scholar
  5. 5.
    Douglas, R.J., Martin, K.A.: Neuronal circuits of the neocortex. Annual Review of Neuroscience 27(1), 419–451 (2004)CrossRefGoogle Scholar
  6. 6.
    Dean, T.: Learning invariant features using inertial priors. Annals of Mathematics and Artificial Intelligence 47, 223–250 (2006)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Rabinovich, M.I., Varona, P., Selverston, A.I., Abarbanel, H.D.I.: Dynamical principles in neuroscience. Reviews of Modern Physics 78(4), 1213+ (2006)CrossRefGoogle Scholar
  8. 8.
    Pöppel, E.: A hierarchical model of temporal perception. Trends in Cognitive Sciences 1(2), 56–61 (1997)CrossRefGoogle Scholar
  9. 9.
    Hawkings, J.: On Intelligence. Cambridge University Press, Cambridge (1991)Google Scholar
  10. 10.
    Numenta: Problems that fit htm, Numenta, Tech. Rep. (2006)Google Scholar
  11. 11.
    George, D., Hawkins, J.: A hierarchical bayesian model of invariant pattern recognition in the visual cortex. In: Proceedings of 2005 IEEE International Joint Conference on Neural Networks, IJCNN 2005, July 4-August, vol. 3, pp. 1812–1817 (2005)Google Scholar
  12. 12.
    Abeles, M.: Corticonics: neural circuits of the cerebral cortex. Henry Holt and Company (2004)Google Scholar
  13. 13.
    Rodríguez, F.B., Huerta, R.: Analysis of perfect mappings of the stimuli through neural temporal sequences. Neural Netw. 17(7), 963–973 (2004)zbMATHCrossRefGoogle Scholar
  14. 14.
    Giegerich, R.: A systematic approach to dynamic programming in bioinformatics. Bioinformatics 16(8), 665–677 (2000)CrossRefGoogle Scholar
  15. 15.
    Kadous, M.W.: Australian sign language signs data set, UCI Machine Learning Repository, Tech. Rep., http://archive.ics.uci.edu/ml/datasets/
  16. 16.
    Kadous, M.W.: Temporal classification: Extending the classification paradigm to multivariate time series. Ph.D. dissertation, The University of New South Wales (2002)Google Scholar
  17. 17.
    Tomasz Kapuscinski, M.W.: Computer Recognition Systems 3, vol. 57, pp. 355–362. Springer, Heidelberg (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • David Rozado
    • 1
  • Francisco B. Rodriguez
    • 1
  • Pablo Varona
    • 1
  1. 1.Grupo de Neurocomputación Biológica (GNB) Dpto. de Ingeniería Informática, Escuela Politécnica SuperiorUniversidad Autónoma de Madrid. Calle Francisco Tomás y Valiente, 11MadridSpain

Personalised recommendations